fix(llmobs): fix crew ai type error

[lievan]

Fixes a TypeError with crewai>=1.121.0 caused by crew ai supporting empty context

Also updates the crewai version we test with to be a min compatible version with 1.121.0

Checklist

• PR author has checked that all the criteria below are met
• The PR description includes an overview of the change
• The PR description articulates the motivation for the change
• The change includes tests OR the PR description describes a testing strategy
• The PR description notes risks associated with the change, if any
• Newly-added code is easy to change
• The change follows the library release note guidelines
• The change includes or references documentation updates if necessary
• Backport labels are set (if applicable)

Reviewer Checklist

• Reviewer has checked that all the criteria below are met
• Title is accurate
• All changes are related to the pull request's stated goal
• Avoids breaking API changes
• Testing strategy adequately addresses listed risks
• Newly-added code is easy to change
• Release note makes sense to a user of the library
• If necessary, author has acknowledged and discussed the performance implications of this PR as reported in the benchmarks PR comment
• Backport labels are set in a manner that is consistent with the release branch maintenance policy

[github-actions]

CODEOWNERS have been resolved as:

.riot/requirements/158ac30.txt                                          @DataDog/apm-python
.riot/requirements/16628a6.txt                                          @DataDog/apm-python
.riot/requirements/181e571.txt                                          @DataDog/apm-python
.riot/requirements/321c69b.txt                                          @DataDog/apm-python
.riot/requirements/8b0105d.txt                                          @DataDog/apm-python
.riot/requirements/f27aa11.txt                                          @DataDog/apm-python
releasenotes/notes/crewai-fix-8d66e3489f87d046.yaml                     @DataDog/apm-python
ddtrace/contrib/integration_registry/registry.yaml                      @DataDog/apm-core-python @DataDog/apm-idm-python
ddtrace/llmobs/_integrations/crewai.py                                  @DataDog/ml-observability
lib-injection/sources/min_compatible_versions.csv                       @DataDog/apm-core-python
min_compatible_versions.csv                                             @DataDog/apm-core-python
riotfile.py                                                             @DataDog/apm-python
supported_versions_output.json                                          @DataDog/apm-core-python
supported_versions_table.csv                                            @DataDog/apm-core-python

[github-actions]

Bootstrap import analysis

Comparison of import times between this PR and base.

Summary

The average import time from this PR is: 234 ± 4 ms.

The average import time from base is: 236 ± 3 ms.

The import time difference between this PR and base is: -1.9 ± 0.2 ms.

Import time breakdown

The following import paths have shrunk:

ddtrace.auto 1.940 ms (0.83%)

ddtrace.bootstrap.sitecustomize 1.266 ms (0.54%)

ddtrace.bootstrap.preload 1.266 ms (0.54%)

ddtrace.internal.remoteconfig.client 0.619 ms (0.26%)

ddtrace 0.674 ms (0.29%)

ddtrace.internal._unpatched 0.024 ms (0.01%)

[pr-commenter]

Benchmarks

Benchmark execution time: 2025-05-29 15:34:41

Comparing candidate commit 1e3f7f2 in PR branch evan.li/crew-fix with baseline commit 074b3be in branch main.

Found 2 performance improvements and 4 performance regressions! Performance is the same for 503 metrics, 7 unstable metrics.

scenario:iastaspects-replace_aspect

• 🟥 execution_time [+600.417ns; +658.983ns] or [+12.645%; +13.878%]

scenario:iastaspectsospath-ospathjoin_aspect

• 🟥 execution_time [+1.121µs; +1.186µs] or [+18.233%; +19.293%]

scenario:iastaspectsospath-ospathsplit_aspect

• 🟥 execution_time [+718.221ns; +901.967ns] or [+14.675%; +18.429%]

scenario:iastaspectsospath-ospathsplitdrive_aspect

• 🟥 execution_time [+444.632ns; +495.589ns] or [+12.130%; +13.520%]

scenario:iastdjangostartup-appsec

• 🟩 execution_time [-1.100s; -1.004s] or [-55.765%; -50.939%]

scenario:iastdjangostartup-tracer

• 🟩 execution_time [-866.546ms; -756.149ms] or [-49.279%; -43.001%]